| Autor: |
Genbao Wang, Yejian Xue, Yafei Qiao, Chunyang Song, Qing Ming, Shuang Tian, Yonggao Xia |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Energies, Vol 17, Iss 23, p 6052 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
1996-1073 |
| DOI: |
10.3390/en17236052 |
| Popis: |
Accurately estimating the state of charge (SOC) of lithium-ion batteries is of great significance for extending battery lifespan and enhancing the efficiency of energy management. Regarding the issue of the relatively low estimation accuracy of SOC by the backpropagation neural network (BPNN), an enhanced dung beetle optimizer (DBO) algorithm is proposed to optimize the initial weights and thresholds of the BPNN. This overcomes the drawback of a single BP neural network being prone to local optimum and accelerates the convergence rate. Simulation analyses on the experimental data of NCM and A123 lithium batteries were conducted in Matlab R2022a. The results indicate that the proposed algorithm in this paper has an average SOC estimation error of less than 1.6% and a maximum error within 2.9%, demonstrating relatively high estimation accuracy and robustness, and it holds certain theoretical research significance. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
